Benchmarks
Gbaeval
Models scored
16
Best score
0.74
Metric
Overall score
Gbaeval is an AI evaluation tracked by Epoch AI, with 16 scored model versions on record. The scores here are reported by third parties rather than produced by Epoch AI running the evaluation itself.
Scored models span February 2026 to June 2026. The best score recorded is 0.74, measured as Overall score. Models come from Anthropic, OpenAI, Google, MiniMax, Moonshot, Google DeepMind, Alibaba, Z.ai (Zhipu AI).
Full record
- Score metric
- Overall score
- Models scored
- 16
- Best score recorded
- 0.74
- Earliest model scored
- Feb 5, 2026
- Most recent model scored
- Jun 16, 2026
- Third-party reported
- Yes
Leaderboard
| 01 | claude-fable-5_unknown | Anthropic | 0.74 |
| 02 | claude-opus-4-8_unknown | Anthropic | 0.71 |
| 03 | gpt-5.5_unknown | OpenAI | 0.53 |
| 04 | claude-sonnet-4-6_unknown | Anthropic | 0.49 |
| 05 | claude-opus-4-6_unknown | Anthropic | 0.44 |
| 06 | claude-opus-4-7_unknown | Anthropic | 0.44 |
| 07 | gpt-5.4-2026-03-05_unknown | OpenAI | 0.32 |
| 08 | gemini-3.5-flash_unknown | 0.07 | |
| 09 | MiniMax-M3 | MiniMax | 0.01 |
| 10 | kimi-k2.6 | Moonshot | 0.01 |
| 11 | kimi-k2.7-code | Moonshot | 0.01 |
| 12 | gemini-3.1-pro-preview | Google DeepMind | 0.01 |
| 13 | qwen3.7-max | Alibaba | 0 |
| 14 | glm-5.2_unknown | Z.ai (Zhipu AI) | 0 |
| 15 | MiniMax-M2.7 | MiniMax | 0 |
| 16 | glm-5.1 | Z.ai (Zhipu AI) | 0 |
More benchmarks
SourceEpoch AI, 'AI Benchmarking Hub'. Published online at epoch.ai. Retrieved 2026-07-29 from https://epoch.ai/benchmarks. Licensed under CC BY 4.0.
← All benchmarks